Strategic House Price Indexes for Warsaw: An Evaluation of Competing Methods

Using a detailed micro-level dataset we compute house price indexes (HPIs) for Warsaw over the period 2006 to 2018. We find that when a hedonic approach is used, the resulting index is reasonably robust to the choice of method. Nevertheless, the hedonic HPIs computed by the National Bank of Poland (NBP) and Statistics Poland (SP) both have some weaknesses. More problematic than hedonic indexes are HPIs computed using the repeat-sales method, which is widely used in the US. We find that such indexes are unreliable, suffering from sample selection bias, and prone to significant revisions when new periods are added to the dataset. Overall, we recommend using either the hedonic time-dummy or rolling time dummy (RTD) methods. These methods when applied to our dataset provide the most reliable HPIs for Warsaw.